Enabling Runtime Logging with MultimodalConversableAgent breaks with the following traceback:
Traceback (most recent call last):
File "/home/mdaum/numbersstation/hive/test_multimodal.py", line 32, in <module>
user_proxy.initiate_chat(
File "/home/mdaum/.cache/pypoetry/virtualenvs/mlcore--_phYNl_-py3.11/lib/python3.11/site-packages/autogen/agentchat/conversable_agent.py", line 1102, in initiate_chat
self.send(msg2send, recipient, silent=silent)
File "/home/mdaum/.cache/pypoetry/virtualenvs/mlcore--_phYNl_-py3.11/lib/python3.11/site-packages/autogen/agentchat/conversable_agent.py", line 738, in send
recipient.receive(message, self, request_reply, silent)
File "/home/mdaum/.cache/pypoetry/virtualenvs/mlcore--_phYNl_-py3.11/lib/python3.11/site-packages/autogen/agentchat/conversable_agent.py", line 902, in receive
reply = self.generate_reply(messages=self.chat_messages[sender], sender=sender)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mdaum/.cache/pypoetry/virtualenvs/mlcore--_phYNl_-py3.11/lib/python3.11/site-packages/autogen/agentchat/conversable_agent.py", line 2056, in generate_reply
final, reply = reply_func(self, messages=messages, sender=sender, config=reply_func_tuple["config"])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mdaum/.cache/pypoetry/virtualenvs/mlcore--_phYNl_-py3.11/lib/python3.11/site-packages/autogen/agentchat/contrib/multimodal_conversable_agent.py", line 120, in generate_oai_reply
response = client.create(context=messages[-1].pop("context", None), messages=messages_with_b64_img)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mdaum/.cache/pypoetry/virtualenvs/mlcore--_phYNl_-py3.11/lib/python3.11/site-packages/autogen/oai/client.py", line 810, in create
log_chat_completion(
File "/home/mdaum/.cache/pypoetry/virtualenvs/mlcore--_phYNl_-py3.11/lib/python3.11/site-packages/autogen/runtime_logging.py", line 85, in log_chat_completion
autogen_logger.log_chat_completion(
File "/home/mdaum/.cache/pypoetry/virtualenvs/mlcore--_phYNl_-py3.11/lib/python3.11/site-packages/autogen/logger/file_logger.py", line 102, in log_chat_completion
source_name = source.name
^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'name'
# Ref: https://microsoft.github.io/autogen/docs/notebooks/agentchat_lmm_gpt-4v/
import os
import autogen
from autogen.agentchat.contrib.multimodal_conversable_agent import MultimodalConversableAgent
import autogen.runtime_logging
config_list_gpt4 = [{"model": "gpt-4o", "api_key": os.environ["OPENAI_API_KEY"]}]
gpt4_llm_config = {"config_list": config_list_gpt4, "cache_seed": 42}
image_agent = MultimodalConversableAgent(
name="image-explainer",
max_consecutive_auto_reply=10,
llm_config=gpt4_llm_config,
)
user_proxy = autogen.UserProxyAgent(
name="User_proxy",
system_message="A human admin.",
human_input_mode="NEVER", # Try between ALWAYS or NEVER
max_consecutive_auto_reply=0,
code_execution_config={
"use_docker": False
}, # Please set use_docker=True if docker is available to run the generated code. Using docker is safer than running the generated code directly.
)
# When this line is not commented out, running this script fails.
autogen.runtime_logging.start(logger_type="file")
# Ask the question with an image
user_proxy.initiate_chat(
image_agent,
message="""What's the breed of this dog?
<img https://th.bing.com/th/id/R.422068ce8af4e15b0634fe2540adea7a?rik=y4OcXBE%2fqutDOw&pid=ImgRaw&r=0>.""",
)I expected the same outputs (plus logs) as when runtime logging is not started.
Describe the bug
Enabling Runtime Logging with MultimodalConversableAgent breaks with the following traceback:
Steps to reproduce
Model Used
gpt-4o
Expected Behavior
I expected the same outputs (plus logs) as when runtime logging is not started.
Screenshots and logs
No response
Additional Information
AutoGen version:
pyautogen-0.3.0Python version: 3.11